The objective of computer vision research is to endow computers with human-like perception to enable the capability to detect their surroundings, interpret the data they sense, take appropriate actions, and learn from...
详细信息
The objective of computer vision research is to endow computers with human-like perception to enable the capability to detect their surroundings, interpret the data they sense, take appropriate actions, and learn from their experiences to improve future performance. The area has progressed from using traditional pattern recognition and imageprocessing technologies to advanced techniques in image understanding such as model-based and knowledge-based vision. In the past few years, there has been a surge of interest in machine learning algorithms for computer vision-based applications. machine learning technology has the potential to significantly contribute to the development of flexible and robust vision algorithms that will improve the performance of practical vision systems with a higher level of competence and greater generality. Additionally, the development of machine learning-based architectures has the potential to reduce system development time while simultaneously achieving the above-stated performance improvements. This work proposes utilizing a computer vision-based approach that leverages machine and deep learning systems to aid the detection and identification of sow reproduction cycles by segmentation and object detection techniques. A lightweight machine learning system is proposed for object detection to address dataset collection issues in one of the most crucial and potentially lucrative farming applications. This technique was designed to detect the vulvae region in pre-estrous sows using a single thermal image. In the first experiment, the support vector machine (SvM) classifier was used after extracting features determined by 12 Gabor filters. The features are then concatenated with the features obtained from the Histogram of oriented gradients (HOG) to produce the results of the first experiment. In the second experiment, the number of distinct Gabor filters used was increased from 12 to 96. The system is trained on cropped image windows and us
machinevision-based applications have witnessed widespread adoption in diverse fields. Efficiently processing and compressing the vast amounts of video data collected by machines is crucial for these applications. To...
详细信息
With the penetration of IoT across sectors, image classification becomes a critical issue if the computations have to be done at the edge. The evolution of low-cost devices with powerful processing for any vision-base...
详细信息
Sonar image segmentation technique is crucial for underwater target tracking, among other things. Due to the undersea environment's influence, noise is easily absorbed, which leads to a poor tracking performance. ...
详细信息
machinevision is a technology and method used to provide automated image-driven analysis in applications such as inspection, process control, and guidance, and is very popular in industries nowadays. Computer/machine...
详细信息
machinevision is a technology and method used to provide automated image-driven analysis in applications such as inspection, process control, and guidance, and is very popular in industries nowadays. Computer/machinevision has been extensively developed and used in production to achieve precise automatic control. This paper presented an imageprocessing approach, a subset of machinevision, for the visual inspection system of the Clutch Friction Disc (CFD) produced for 2 wheelers. imageprocessing is used to inspect different parts of the CFD. After previous operations of production, a part enters the inspection system, where the geometry and size of the part are inspected, and then imageprocessing technology is used to decide to accept or reject the product. This paper presented the work constructed using a python program with OpenCv which aims to identify the major defects in clutch friction plates, by using different imageprocessing techniques. With the proposed approach decision can be made automatically that whether the processed part will be accepted or rejected and then will be identified as "Ok tested" and "Faulty" pieces. Copyright (C) 2022 Elsevier Ltd. All rights reserved.
With the development of imageprocessing technology, computer vision technology has been widely applied in the field of motion training. How to effectively restore blurred images during motion training and achieve ded...
详细信息
image classification is a core task in the field of computer vision, with significant implications for applications such as medical imaging and autonomous driving. Classical neural network architectures face numerous ...
详细信息
ISBN:
(纸本)9798331507800;9798331507794
image classification is a core task in the field of computer vision, with significant implications for applications such as medical imaging and autonomous driving. Classical neural network architectures face numerous challenges when dealing with high-dimensional and complex data, particularly in terms of feature extraction and data processing capabilities, limiting their performance in certain applications. Quantum computing offers promising new approaches to processing high dimensional complex data, most notably through Parameterized Quantum Circuits (PQC) as quantum hybrid neural networks for image classification. In this paper, we propose a hybrid neural network featuring a specific PQC structure designed to generate entanglement in accordance with sample images. This PQC structure utilizes the adjacency matrix of the corresponding graph of the sample image, embedding adjacency relationships among nodes into the entanglement module, thereby generating entanglement aligned with the features of specific images. Numerical results validate the effectiveness of our PQC model across various image classification tasks, enhancing the efficiency of feature learning and representation. Our model demonstrates significant advantages in classification accuracy and learning efficiency on classical datasets. Our research not only advances the theoretical understanding of hybrid quantum networks but also paves the way for practical implementations in real-world scenarios.
Crack is an important factor to consider when assessing the quality of concrete structures since it impacts the structure's longevity, application, and safety. Convolutional neural networks are increasingly the be...
详细信息
ISBN:
(纸本)9798350350470;9798350350487
Crack is an important factor to consider when assessing the quality of concrete structures since it impacts the structure's longevity, application, and safety. Convolutional neural networks are increasingly the best option to replace manual crack detection because of the advancement of methods for deep learning. machine learning algorithms known as artificial neural networks (ANNs) imitate how the human brain functions. These Neural Networks can be implemented in software. However, these neural networks require large computations. Hardware implementation of these neural networks has higher processing speeds than their software implementations. CNN is a particular kind of artificial neural network that is used to interpret pixel data and is utilised in image detection and processing. Computer visionapplications including object identification, image segmentation, and image classification work well with convolutional neural networks. employed for categorization The proposed method uses a configurable convolution neural network system for crack detection. An accuracy of 97.5% is achieved over 200 images. By detecting the crack effectively using the method, the quality of the concrete structures will be ensured using dedicated hardware shortly.
The performance of the developed Stitched Foam-filled Honeycomb Sandwich (SFHS) panels with two different stitches spacing were compared to the Foam-filled Honeycomb Sandwich (FHS) panel. The adjacent Stitched Foam-fi...
详细信息
The performance of the developed Stitched Foam-filled Honeycomb Sandwich (SFHS) panels with two different stitches spacing were compared to the Foam-filled Honeycomb Sandwich (FHS) panel. The adjacent Stitched Foam-filled Honeycomb Sandwich (SFHS1) panel exhibited a peak flexural load of 1672 N at a strain rate of 100 mm/min, achieved a velocity of 4.031 m/s during Low velocity Impact (LvI) testing, and demonstrated a compressive strength of 14.19 N/mm(2) in Compression After Impact (CAI) tests performed with a maximum drop height impactor of 700 mm. Matlab imageprocessing was utilized to detect damaged areas that were invisible to the human eye after the LvI test. The experimental data of CAI tests were subjected to a machine Learning (ML) third-order regression algorithm that predicted SFHS1 and alternate Stitched Foam-filled Honeycomb Sandwich (SFHS2) panel would withstand up to a drop height of 1300 mm at 885 N and 845 N respectively, whereas value is far less for FHS panel. The results showcased the effectiveness of through-thickness stitching reinforcement in improving the panel's interfacial, flexural, residual compressive, and impact strengths compared to unstitched panel. The study emphasized the advantage of implementing the SFHS1 panel, which is affordable and lightweight, which makes it appropriate for a wide range of structural applications.
machinevision is a field of computer vision that focuses on developing and implementing automated visual inspection systems. It involves using cameras, sensors, and imageprocessing algorithms to capture and analyze ...
详细信息
暂无评论